Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to someone's first appearance or introduction in a particular field, such as film, music, or literature

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "debut."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sav
    -0.71
    tics
    -0.71
    bara
    -0.68
    esthetic
    -0.67
     Canaver
    -0.66
    par
    -0.65
    akia
    -0.64
    ĵĺ
    -0.64
    axies
    -0.63
     abused
    -0.62
    POSITIVE LOGITS
    antes
    0.97
     debut
    0.94
    iour
    0.86
    iates
    0.82
    iator
    0.81
    ante
    0.79
    antly
    0.77
    iating
    0.76
     foray
    0.74
    iary
    0.72
    Act Density 0.009%

    No Known Activations